A novel fusion framework of infrared and visible images based on RLNSST and guided filter

Abstract

In this paper, we designed a novel image fusion framework based on Redundant Lifting Non-Separable Wavelet-based Shearlet Transform (RLNSST) and guided filter. Specifically, the Non-subsampled Pyramid (NSP) algorithm is substituted with Redundant Lifting Non-Separable Wavelet (RLNSW) in the Non-sub-sampled shearlet transform (NSST) algorithm, which is one of the state-of-the-art multi-scale decomposition algorithms and widely used in image fusion applications. On the other hand, guided filter-based saliency detection algorithm is used to fuse the coefficient matrices obtained by the improved NSST, named as RLNSST in this paper. We first decompose the infrared and visible image into multi-direction and multi-scale coefficient matrices by RLNSST decomposition. Then, Laplacian filter and Gaussian filter is utilized to generate the saliency map. Next, a novel weighted average based on guided filtering to retain edge detail information is used as the fusion rule. Finally, inverse RLNSST transform is used to get the fused image. Experiments show that our method can obtain better performance than other recently developed techniques.